VI

felixchao_vicuna-33b-coder

VicunaGGUF by TheBlokeUpdated 2023-10-21
Download on Hugging Face
Parameters32.5B
Context2K
Layers60
Architecturellama
Smallest quant13.5 GB
Quick answer

felixchao_vicuna-33b-coder needs about 33.2 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 13.5 GB (Q2_K) to 34.6 GB (Q8_0).

Vicuna 33B Coder in GGUF format

Vicuna 33B Coder is a 32.5B parameter model fine‑tuned for coding tasks. It is available in multiple GGUF quantizations from TheBloke. The model supports a 2048 token context window and is released under an other license.

Good at

  • Coding assistance
  • Code generation
  • Programming Q&A

Limits

  • No vision support
  • License not specified
  • Context limited to 2048 tokens

Best for

  • Developers needing local code generation
  • Educational coding tools
  • Automated code review

Who it’s for. Users who want a large‑parameter coding model that can run locally with GGUF support. Ideal for developers and educators who prefer open‑source inference tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.5 GB 17.3 GB
Too big Get file →
Q3_K_S14.1 GB 17.8 GB
Too big Get file →
Q3_K_M15.8 GB 19.5 GB
Too big Get file →
Q3_K_L17.3 GB 21.1 GB
Too big Get file →
Q4_018.4 GB 22.1 GB
Too big Get file →
Q4_K_S18.4 GB 22.2 GB
Too big Get file →
Q4_K_M19.6 GB 23.4 GB
Too big Get file →
Q5_022.4 GB 26.2 GB
Too big Get file →
Q5_K_S22.4 GB 26.2 GB
Too big Get file →
Q5_K_M23.0 GB 26.8 GB
Too big Get file →
Q6_K26.7 GB 30.5 GB
Too big Get file →
Q8_034.6 GB 38.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 18.44 GB, estimated 32 GB memory at 8k context). For 16 GB VRAM, Q5_K_M (23.05 GB, 36.6 GB memory) or Q4_K_M (19.62 GB, 33.2 GB memory). For 32 GB VRAM, Q6_K (26.69 GB, 40.3 GB memory) or Q8_0 (34.57 GB, 48.2 GB memory).

What GPU do you need for felixchao_vicuna-33b-coder?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q4_K_S (18.4 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 40.3 GB in use).

Which felixchao_vicuna-33b-coder quant should you choose?

Q4_K_M is the usual starting point for felixchao_vicuna-33b-coder: it balances file size and quality well. Here it is a 19.6 GB file.

The Q8_0 file is 34.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 13.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters32.5B
Layers60
Trained context2,048 tokens
KV cache (fp16)1560 KB per token

Source

Quantized byTheBloke
FamilyVicuna
Licenseother
Downloads (HF)956
Last updated2023-10-21

Frequently asked questions about felixchao_vicuna-33b-coder

How much VRAM does felixchao_vicuna-33b-coder need?

About 33.2 GB at Q4_K_M with an 8K context window. That is the 19.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run felixchao_vicuna-33b-coder on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of felixchao_vicuna-33b-coder GGUF?

It depends on the quant: Q2_K is 13.5 GB, Q3_K_S is 14.1 GB, Q3_K_M is 15.8 GB, Q3_K_L is 17.3 GB, Q4_0 is 18.4 GB, Q4_K_S is 18.4 GB and 6 more.

What context length does felixchao_vicuna-33b-coder support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 13.1 GB at 8K and 3.3 GB at 2K.

Where can I download felixchao_vicuna-33b-coder GGUF?

The files are on Hugging Face in the TheBloke/vicuna-33B-coder-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does felixchao_vicuna-33b-coder use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Use the Q4_K_S quantization; it requires about 32 GB of memory at 8k context, which is beyond 8 GB VRAM. Smaller VRAM requires lower‑bit quantizations not available for this model.

Does this model support image input?

No, the model has no vision capabilities.

What context length does it support?

It supports a 2048 token context window.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Vicuna models

All Vicuna →

Other medium models

All medium models →